Network Node Probe for Workload Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In fog/edge computing environments, identifying suitable computing nodes for workload execution is inefficient as existing methods rely on manual definition of node properties and lack optimization for resource utilization, leading to potential overloading and suboptimal processing.
Innovation Solution
A system and method that integrates a probe into the software application and scheduling module to quickly test and classify computing nodes using a classification scheme, allowing for immediate execution of software applications on suitable nodes, with a cleaning component to remove artefacts and test code that operates within 10-100 milliseconds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual definition of node properties is used to identify suitable computing nodes, then the system is simple to implement, but the resource utilization is suboptimal and processing efficiency is reduced
Solution Approach 1:
The system performs preliminary actions by dispatching probes to test computing nodes before workload assignment. The probes pre-test node properties, capabilities, and availability, storing results for rapid matching with future workloads. This preliminary testing eliminates the need for manual property definition and enables automated, optimized node selection, thereby improving processing efficiency without proportionally increasing system complexity.
Solution Approach 2:
The probe acts as an intermediary between the scheduling module and computing nodes. It carries test code that autonomously evaluates node properties and returns results to the scheduling module. This intermediary mechanism automates the complex task of node assessment, allowing the system to achieve optimal resource utilization without requiring complex manual configuration or management interfaces.
2Reliability
If comprehensive testing of computing nodes is performed to optimize resource utilization, then the resource planning is improved, but the time required for node identification increases
Solution Approach 1:
The system performs comprehensive node testing in advance by dispatching probes that evaluate multiple node properties including processor capabilities, storage capacity, and current workload status. These preliminary tests establish a cached profile of each node's capabilities, which can be rapidly queried during scheduling decisions. This approach ensures reliable resource planning while minimizing real-time identification delays.
Solution Approach 2:
Instead of performing comprehensive tests each time a workload needs assignment, the system creates copies of node capability profiles through probe testing. These profile copies are stored and reused for multiple scheduling decisions, allowing the system to maintain high reliability in resource planning without repeatedly incurring the time cost of comprehensive testing.
3Productivity
If computing nodes are selected without checking for potentially more suitable nodes, then the selection process is fast, but the network utilization is not optimized
Solution Approach 1:
The system implements feedback mechanisms where probe test results provide information about node suitability, current utilization status, and capability matching. The scheduling module uses this feedback to iteratively identify and select the most suitable nodes for each workload. This feedback-driven approach enables the system to optimize network utilization by continuously learning from test results and adjusting node selections accordingly, without requiring overly complex manual evaluation processes.
Data Source
AI summary
A system for finding and identifying computer nodes in a network includes a network having multiple computer nodes and a planning module. The computer nodes are connected to one another by communication connections and are configured to perform a workload of one or more software application(s). The planning module includes at least one probe having a test code and is configured to send the probe with the test code to the computer nodes to test the properties of the computer nodes with respect of their ability to perform a specific workload of at least one software application. The planning module is configured to take the test results as a basis for selecting one or more computer nodes for performing the workload of at least one software application, and to start the performance of the workload of the at least one software application on the selected computer node.